Video dubbing aims to translate original speech in visual media programs from the source language to the target language, relying on neural machine translation and text-to-speech technologies. Due to varying information densities across languages, target speech often mismatches the source speech duration, causing audio-video synchronization issues that significantly impact viewer experience. In this study, we approach duration alignment in LLM-based video dubbing machine translation as a preference optimization problem. We propose the Segment Supervised Preference Optimization (SSPO) method, which employs a segment-wise sampling strategy and fine-grained loss to mitigate duration mismatches between source and target lines. Experimental results demonstrate that SSPO achieves superior performance in duration alignment tasks.
@article{arxiv.2508.08550,
title = {Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference Optimization},
author = {Chaoqun Cui and Liangbin Huang and Shijing Wang and Zhe Tong and Zhaolong Huang and Xiao Zeng and Xiaofeng Liu},
journal= {arXiv preprint arXiv:2508.08550},
year = {2025}
}